integrations.expert_parallel.args
integrations.expert_parallel.args
Pydantic args for the Expert-Parallel (DeepEP) plugin.
Classes
| Name | Description |
|---|---|
| ExpertParallelArgs | Input args for the expert_parallel plugin. See the integration README. |
ExpertParallelArgs
integrations.expert_parallel.args.ExpertParallelArgs()Input args for the expert_parallel plugin. See the integration README.
Attributes
| Name | Description |
|---|---|
| expert_parallel_size | Number of EP ranks. 1 = disabled (default), > 1 = enabled. |
| expert_parallel_token_capacity | Max tokens routed to any single expert per forward; the lowest-weight excess (token,expert) assignments are dropped. DeepEP’s intranode combine deadlocks once one expert is overloaded, and GLM-style routers concentrate more with depth — set this (e.g. 1024) for them. None = no cap. |